{"id":"W4284709654","doi":"10.1145/3510003.3510159","title":"CLEAR","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 44th International Conference on Software Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Task (project management); Natural language processing; Artificial intelligence; Word (group theory); Information retrieval; Embedding; Semantics (computer science); Programming language; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000193863,0.00009176343,0.00008741263,0.0001043148,0.00009249816,0.00007155802,0.001941173,0.0000174411,0.00007074084],"category_scores_gemma":[0.0001897758,0.00008122571,0.0000621352,0.0001804625,0.00001098993,0.0002216829,0.0008813314,0.0002538193,0.00000404398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009192723,"about_ca_system_score_gemma":0.00002985218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005129052,"about_ca_topic_score_gemma":6.682511e-8,"domain_scores_codex":[0.9989398,0.000002832446,0.0001736435,0.0002167706,0.0005323095,0.0001346503],"domain_scores_gemma":[0.9995461,0.00002488099,0.000104182,0.0001354705,0.0001587731,0.00003060068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008277648,0.00002706519,0.001757295,0.00001641054,0.00002238514,6.420047e-7,0.0004217142,0.01321608,0.00218231,0.9797922,0.0003069583,0.002248614],"study_design_scores_gemma":[0.0003289264,0.0001171244,0.002632406,0.0001003848,0.000005321577,0.00003765187,0.0001590496,0.9734926,0.00763559,0.006667995,0.008526174,0.0002968258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5790793,0.00005051709,0.3941197,0.005945843,0.005688906,0.000445614,0.00002522076,0.0009015469,0.01374337],"genre_scores_gemma":[0.9673474,0.000002217306,0.03204747,0.0001443891,0.00005331879,0.00002803036,4.213027e-7,0.000008950239,0.0003677925],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9731243,"threshold_uncertainty_score":0.3607215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02487960478481576,"score_gpt":0.2298718623686812,"score_spread":0.2049922575838654,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}